© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 147389
    Prev
    Next
    INDEX
    Explanations

    chromosome structural

    np_acts-logits-general · gemini-2.5-flash-lite

    polling or repeatedly asking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Astronom
    0.50
     کا
    0.50
     telescopes
    0.49
    Hands
    0.48
    teles
    0.48
     ჭ
    0.48
    Cann
    0.47
     লক্ষ
    0.46
    Ini
    0.46
    Beginning
    0.46
    POSITIVE LOGITS
    elaar
    0.45
     tightness
    0.44
    ບບ
    0.42
    뵌
    0.42
     వైర
    0.41
    प्टेंबर
    0.41
    ड़ों
    0.40
     deliberations
    0.40
    зом
    0.39
    そも
    0.39
    Activations Density 0.001%

    No Known Activations